Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 481
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.42
     final
    -0.38
    law
    -0.38
    مساعدة
    -0.32
     dé
    -0.32
    背
    -0.32
     Autorizaciones
    -0.32
     آخر
    -0.31
    hình
    -0.31
     واس
    -0.31
    POSITIVE LOGITS
    Aholisi
    0.63
    новништво
    0.61
    astify
    0.59
    CharStream
    0.56
     ویکی‌پدی
    0.55
     ſta
    0.55
     كومونز
    0.53
    Personensuche
    0.52
     الرياضيه
    0.52
     ſen
    0.51
    Activations Density 1.032%

    No Known Activations